Instructions to use trl-internal-testing/tiny-DeepseekV3ForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trl-internal-testing/tiny-DeepseekV3ForCausalLM with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="trl-internal-testing/tiny-DeepseekV3ForCausalLM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("trl-internal-testing/tiny-DeepseekV3ForCausalLM")
model = AutoModelForCausalLM.from_pretrained("trl-internal-testing/tiny-DeepseekV3ForCausalLM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use trl-internal-testing/tiny-DeepseekV3ForCausalLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trl-internal-testing/tiny-DeepseekV3ForCausalLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trl-internal-testing/tiny-DeepseekV3ForCausalLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/trl-internal-testing/tiny-DeepseekV3ForCausalLM

SGLang

How to use trl-internal-testing/tiny-DeepseekV3ForCausalLM with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "trl-internal-testing/tiny-DeepseekV3ForCausalLM" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trl-internal-testing/tiny-DeepseekV3ForCausalLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "trl-internal-testing/tiny-DeepseekV3ForCausalLM" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trl-internal-testing/tiny-DeepseekV3ForCausalLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use trl-internal-testing/tiny-DeepseekV3ForCausalLM with Docker Model Runner:
```
docker model run hf.co/trl-internal-testing/tiny-DeepseekV3ForCausalLM
```

albertvillanova HF Staff commited on 3 days ago

Commit

d55cabf

1 Parent(s): ccb0a76

Upload DeepseekV3ForCausalLM (#3)

Browse files

- Upload DeepseekV3ForCausalLM (4ad2a63eb323852e57569ea3a2afc7053b84f9e1)

Files changed (3) hide show

config.json +2 -2
generation_config.json +1 -1
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -21,7 +21,7 @@
   "n_routed_experts": 256,
   "n_shared_experts": 1,
   "norm_topk_prob": true,
-  "num_attention_heads": 4,
   "num_experts_per_tok": 8,
   "num_hidden_layers": 2,
   "num_key_value_heads": 2,
@@ -37,7 +37,7 @@
   "routed_scaling_factor": 2.5,
   "tie_word_embeddings": false,
   "topk_group": 4,
-  "transformers_version": "4.57.3",
   "use_cache": true,
   "v_head_dim": 128,
   "vocab_size": 128815

   "n_routed_experts": 256,
   "n_shared_experts": 1,
   "norm_topk_prob": true,
+  "num_attention_heads": 2,
   "num_experts_per_tok": 8,
   "num_hidden_layers": 2,
   "num_key_value_heads": 2,
   "routed_scaling_factor": 2.5,
   "tie_word_embeddings": false,
   "topk_group": 4,
+  "transformers_version": "4.56.2",
   "use_cache": true,
   "v_head_dim": 128,
   "vocab_size": 128815

generation_config.json CHANGED Viewed

@@ -5,5 +5,5 @@
   "eos_token_id": 1,
   "temperature": 0.6,
   "top_p": 0.95,
-  "transformers_version": "4.57.3"
 }

   "eos_token_id": 1,
   "temperature": 0.6,
   "top_p": 0.95,
+  "transformers_version": "4.56.2"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bb900594a8201ed0be43c96f9d402137954b73d19c677167a24e4af1440be95
-size 11036056

 version https://git-lfs.github.com/spec/v1
+oid sha256:236f4470999e17d8ce9c9f242dd2edeff18fea9fe3928b08d36e95d3b56c01e2
+size 7619984